File size: 5,777 Bytes
ec0a9aa | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 | {
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "d622b051",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import re\n",
"import glob\n",
"import pandas as pd\n",
"import pyarrow.parquet as pq\n",
"from tqdm import tqdm\n",
"\n",
"ROOT = \"./droid_1.0.1_first_20_chunks\"\n",
"NUM_CHUNKS = 20\n",
"OUT_CSV = \"droid_first_20_chunks_markovian_split.csv\"\n",
"\n",
"MARKOVIAN_KEYWORDS = [\n",
" \"pick up\", \"pick\", \"grasp\", \"grab\", \"lift\",\n",
" \"place\", \"put\", \"move\", \"push\", \"pull\",\n",
" \"open\", \"close\", \"turn on\", \"turn off\",\n",
" \"press\", \"insert\", \"remove\", \"slide\",\n",
"]\n",
"\n",
"NON_MARKOVIAN_KEYWORDS = [\n",
" \"then\", \"after\", \"before\", \"first\", \"second\", \"third\", \"finally\", \"next\",\n",
" \"all\", \"every\", \"each\", \"remaining\", \"another\",\n",
" \"sort\", \"arrange\", \"organize\", \"clean up\", \"cleanup\",\n",
" \"stack\", \"unstack\", \"set up\", \"prepare\",\n",
" \"repeat\", \"again\", \"until\",\n",
" \"in order\", \"sequence\",\n",
"]\n",
"\n",
"\n",
"def normalize_text(x):\n",
" if x is None:\n",
" return \"\"\n",
" return str(x).lower().strip()\n",
"\n",
"\n",
"def classify_task(text):\n",
" text = normalize_text(text)\n",
"\n",
" non_score = 0\n",
" markov_score = 0\n",
"\n",
" for kw in NON_MARKOVIAN_KEYWORDS:\n",
" if re.search(rf\"\\b{re.escape(kw)}\\b\", text):\n",
" non_score += 2\n",
"\n",
" for kw in MARKOVIAN_KEYWORDS:\n",
" if re.search(rf\"\\b{re.escape(kw)}\\b\", text):\n",
" markov_score += 1\n",
"\n",
" # Multiple action verbs usually means longer-horizon behavior\n",
" action_count = sum(\n",
" 1 for kw in MARKOVIAN_KEYWORDS\n",
" if re.search(rf\"\\b{re.escape(kw)}\\b\", text)\n",
" )\n",
"\n",
" if action_count >= 2 and any(w in text for w in [\"then\", \"after\", \"before\", \"and\"]):\n",
" non_score += 2\n",
"\n",
" # Broad household goals are often non-Markovian because progress matters\n",
" broad_goal_words = [\"clean\", \"tidy\", \"organize\", \"arrange\", \"sort\"]\n",
" if any(w in text for w in broad_goal_words):\n",
" non_score += 2\n",
"\n",
" if non_score > markov_score:\n",
" return \"non_markovian\"\n",
"\n",
" return \"markovian\"\n",
"\n",
"\n",
"def read_episode_summary(parquet_path):\n",
" columns = [\n",
" \"episode_index\",\n",
" \"task_index\",\n",
" \"language_instruction\",\n",
" \"language_instruction_2\",\n",
" \"language_instruction_3\",\n",
" \"task_category\",\n",
" \"is_episode_successful\",\n",
" ]\n",
"\n",
" table = pq.read_table(\n",
" parquet_path,\n",
" columns=[c for c in columns if c in pq.read_schema(parquet_path).names],\n",
" )\n",
"\n",
" df = table.slice(0, 1).to_pandas()\n",
" row = df.iloc[0].to_dict()\n",
"\n",
" instruction_parts = [\n",
" row.get(\"language_instruction\", \"\"),\n",
" row.get(\"language_instruction_2\", \"\"),\n",
" row.get(\"language_instruction_3\", \"\"),\n",
" row.get(\"task_category\", \"\"),\n",
" ]\n",
"\n",
" instruction_text = \" | \".join(\n",
" [normalize_text(x) for x in instruction_parts if normalize_text(x)]\n",
" )\n",
"\n",
" return {\n",
" \"episode_index\": row.get(\"episode_index\"),\n",
" \"task_index\": row.get(\"task_index\"),\n",
" \"language_instruction\": row.get(\"language_instruction\", \"\"),\n",
" \"language_instruction_2\": row.get(\"language_instruction_2\", \"\"),\n",
" \"language_instruction_3\": row.get(\"language_instruction_3\", \"\"),\n",
" \"task_category\": row.get(\"task_category\", \"\"),\n",
" \"is_episode_successful\": row.get(\"is_episode_successful\"),\n",
" \"instruction_text\": instruction_text,\n",
" \"label\": classify_task(instruction_text),\n",
" \"parquet_path\": parquet_path,\n",
" }\n",
"\n",
"\n",
"all_files = []\n",
"\n",
"for i in range(NUM_CHUNKS):\n",
" chunk = f\"chunk-{i:03d}\"\n",
" pattern = os.path.join(ROOT, \"data\", chunk, \"*.parquet\")\n",
" all_files.extend(sorted(glob.glob(pattern)))\n",
"\n",
"print(f\"Found {len(all_files)} parquet files\")\n",
"\n",
"rows = []\n",
"\n",
"for path in tqdm(all_files):\n",
" try:\n",
" rows.append(read_episode_summary(path))\n",
" except Exception as e:\n",
" rows.append({\n",
" \"episode_index\": None,\n",
" \"task_index\": None,\n",
" \"instruction_text\": \"\",\n",
" \"label\": \"read_error\",\n",
" \"parquet_path\": path,\n",
" \"error\": str(e),\n",
" })\n",
"\n",
"df = pd.DataFrame(rows)\n",
"\n",
"df.to_csv(OUT_CSV, index=False)\n",
"\n",
"print(df[\"label\"].value_counts())\n",
"print(f\"Saved to {OUT_CSV}\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"version": "3.10.19"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|